Method and apparatus for monitoring an industrial plant

Abstract

The invention relates to a method for monitoring an industrial plant (2) comprising plant objects, in which method the following steps are carried out: receiving (S1) a video stream (VS) of the plant (2), which is generated using a video camera device (3), wherein the video stream (VS) contains a temporal sequence of two-dimensional image data; assigning (S2) two-dimensional image components (PT) of the video stream (VS) to plant objects (A', B', C', D') using a three-dimensional (3D) model (CAD) of the plant (2), through which respective object properties (XYZ) are assigned to the plant objects (A', B', C', D'); determining (S3) a recording property of the image data depending on the image components (PT) and the respective object property (XYZ) assigned to one or more plant objects (C'), wherein the recording property is a position, an alignment and / or a zoom factor of the video camera device (3) delivering the video stream; and outputting (S4) the video stream (VS') together with the determined object properties (XYZ) and / or recording properties.

Description

[0001] Method and device for monitoring an industrial plant

[0002] The present invention relates to a method and a device for observing or monitoring an industrial plant. Furthermore, a computer program product is proposed that functionalizes program-controllable devices such that they carry out a method for monitoring an industrial plant.

[0003] Industrial facilities, such as factories, especially in the chemical industry, distribution systems for raw materials or processed products, and even industrial logistics systems, are typically visually monitored or recorded using video cameras. To reliably monitor the complex, interconnected system objects of an industrial facility, multiple surveillance cameras are typically used to monitor a specific spatial area and provide video streaming data.

[0004] It is desirable to be able to reliably evaluate such real-time video data and intervene in the event of irregularities in system behavior. In the past, video camera systems were distributed across the spatial areas to be monitored and, for example, mounted for pivoting or equipped with a zoom function. Often, the generated video streams contain no additional information other than the video data, so the specific location of the surveillance camera providing the video stream or its settings remained unknown. In the past, therefore, monitoring of the displayed videos or films was primarily carried out manually.

[0005] It is particularly desirable to simplify the visual monitoring of industrial facilities using video streams. It is particularly desirable to provide information beyond image data or video sequences. Existing monitoring systems for industrial facilities typically only provide image data.

[0006] The mapping of two-dimensional image data components of industrial plants to existing three-dimensional (3D) plant models is described in N. Navab et al.: "Cyclicon: a software platform for the creation and update of virtual factories", 1999 IEEE, pages 459-463, 1999 7th IEEE International Conference on Emerging Technologies and Factory Automation. Proceedings ETFA '99, ISBN: 0-7803-5670-5. Cyclicon allows the superimposed display of two-dimensional projections of the three-dimensional plant model onto the two-dimensional image data. However, this requires the prior mapping of the known configuration of the surveillance camera to specific 3D model data and vice versa. Furthermore, the user may be prompted to mark certain predefined pixels in the 2D image data so that the video stream can be overlaid.

[0007] In the current state of the art, a necessary prerequisite for image analysis is that the origin and contextual content of the two-dimensional image data are specified. In practice, this is generally not the case, particularly because there are numerous video streams from different cameras whose recording settings, orientations, and other properties are undocumented. Furthermore, the cameras are often not fixed but can be rotated. Manual annotation of the video stream data by the user while the video stream is running is therefore practically impossible.

[0008] Against this background, it is an object of the present invention to provide an improved method for monitoring industrial plants, in particular with many video camera devices and plant objects.

[0009] Accordingly, a method for monitoring an industrial plant with plant objects is proposed, which comprises the steps:

[0010] Receiving a video stream of the system generated by a video camera device, the video stream containing a temporal sequence of two-dimensional image data;

[0011] Assigning two-dimensional image components of the video stream to system objects using a three-dimensional model of the system in which the system objects are assigned respective object properties;

[0012] Determining a recording property of the image data depending on the image component(s) assigned to one or more plant objects and the respective object property, wherein the recording property comprises a position, an orientation and / or a zoom factor of the video camera device which captures the video stream; and

[0013] Output the video stream along with the specified object properties and / or recording properties.

[0014] The video stream is received, in particular, at a monitoring location remote from the position of the video camera device. The video camera device is therefore installed at an unknown location when receiving the video stream. At the monitoring location, the recording properties are not directly observable but are advantageously derived from the two-dimensional image components and the three-dimensional model of the system. The process steps, in particular those of assignment and determination, are preferably carried out automatically. The automated execution can be computer-implemented in the background, without a user explicitly retrieving the recording properties and object properties.

[0015] An industrial facility is understood, in particular, as a system of technical facilities that interact with one another and serve, for example, to manufacture, process, or transport materials. The technical facilities can be understood as plant objects or plant components. Examples of industrial facilities include an infrastructure facility for water and / or wastewater, cooling towers, electrical distribution systems, tank farms, and utility facilities. In some embodiments, the monitored industrial facility is a facility in the chemical industry.

[0016] In this method, context information relating to the camera and / or the plant object captured in the video stream is determined from the image data received from a video camera device, such as a digital surveillance camera, or from a video stream containing a temporal sequence of two-dimensional image data. By outputting the video stream and / or a two-dimensional image together with the specific object or recording properties, the status of the monitored industrial plant can be better classified.

[0017] A recording property is understood to be a property attributable to the video stream or an individual two-dimensional image datum that depends on the creation of the respective image. This can be, for example, an angle of view, a crop, a recording position, and the orientation of the video camera. Exposure settings can also be considered a recording property. One can also refer to camera properties.

[0018] It is also possible that environmental conditions such as light, dark, weather conditions and the like are taken into account when determining the recording properties.

[0019] An image component can be, for example, a section of the overall image or an image data set created by filtering.

[0020] For example, a three-dimensional plant model similar to a CAD model can be used, in which the plant objects, i.e., the components of the industrial plant, are provided with known object properties. Object properties include, in particular, a location, a size or dimension, the alignment or orientation, as well as a list of subcomponents or material and surface properties of the respective plant object. Also conceivable as object properties is a list of assignable static or dynamic data, such as, but not limited to, material and construction details, flow media and parameters such as substance, flow, temperature, pressure, or manipulated and controlled variables of valves.

[0021] Through an analysis of two-dimensional image components, particularly a computer-implemented analysis, the position, orientation, or zoom factor of the respective video camera device can be deduced. This means that with the help of the proposed method, the obtained two-dimensional image data sequences in the form of a video stream, using a suitable three-dimensional model of the industrial plant, can be used to more closely characterize recording conditions or the video camera device aimed at the image component or a specific plant object as recording properties. Without the need to collect additional data, the recording properties are obtained with regard to the orientation, i.e. the direction in which the surveillance camera is pointing, and the detectable image angle or the currently set zoom factor of the surveillance camera. The orientation can be specified in a local or global coordinate system.

[0022] In embodiments, the one or more video camera devices have a video capture area. The video capture area comprises a spatial environment of the respective video camera device and is defined, for example, by the camera properties, such as its capture angle, panning capabilities, zoom capabilities, resolution, light sensitivity, and the like. In a permanently installed video camera device with fixed focus and zoom, the video stream acquired by the video camera device displays a fixed image section, which thus forms the video capture area of ​​the environment.

[0023] In some embodiments, the industrial plant is located on a spatial site or a plant site. Typically, the respective video detection area is smaller than the plant site. For example, only a plurality of partially overlapping video detection areas of several video camera systems cover the plant site. In some embodiments, the video detection areas are located on the plant site, but can be independent of each other or spatially separated by unmonitored areas.

[0024] In embodiments, the video camera device is arranged on the plant site, and the three-dimensional model of the plant comprises the plant site, in particular the entire plant site. The step of determining a recording property then preferably comprises: determining the position of the video camera device within the plant site and more preferably within the video capture area.

[0025] In embodiments, the position of the video camera device is output in the global and / or local coordinate system,

[0026] The global coordinate system can be related to the plant site, and the local coordinate system to the respective video capture area. In embodiments, the three-dimensional model of the plant covers the plant site in the global coordinate system, and the position of the video camera device is determined in the global coordinate system, preferably also in the local coordinate system. The video capture area therefore preferably covers the local coordinate system.

[0027] This improves observation or monitoring of the plant. If an event occurs, such as a malfunction, personnel can locate and reach the scene of the accident more quickly and easily. The automated addition of recording and / or object data that cannot be derived from the video stream alone facilitates the evaluation of the current plant status or situation. This can be used to manage a malfunction, but also generally for evaluation, optimization, and simplified plant operation.

[0028] In some embodiments, the surveillance camera itself is captured as part of the system, i.e., as a system object in the 3D model. It is possible that the location or position of the respective camera is known and used to determine the orientation and zoom factor.

[0029] Advantageously, the video stream is output together with the object or recording properties so that comprehensive image information can be provided, for example in a mobile device with a display device or a control room for monitoring industrial plants.

[0030] In this respect, in embodiments, the video stream is displayed together with the object properties and the recording properties using a display device.

[0031] Monitoring a system also includes, in particular, observing, evaluating, and optimizing through improved information provision. Therefore, collecting or deriving information about the "monitored" system using video stream data is considered monitoring.

[0032] In embodiments of the method, the following step is performed: Creating a database that assigns further functional properties and / or context data to the system objects. The functional properties include, for example, process data, temperatures, or flow materials. In embodiments, the context data can include, in particular, time data, weather data, and / or visibility conditions. The aforementioned assignable static or dynamic data can be considered as context data.

[0033] In particular, the database can be linked to the three-dimensional model of the system, so that the respective recorded system object can be identified using the three-dimensional model data and the functional properties from an image component. In particular, the camera position, its orientation, and / or the zoom factor can be determined based on the identification of system objects in image components and the object properties stored in the 3D model, such as size, positioning, or orientation.

[0034] In particular, image processing methods, as mentioned in the introduction, are suitable for this purpose. In embodiments of the method, the functional properties and / or the context data are updated, particularly in real time.

[0035] The method can be used, for example, to determine dynamic recording properties using a temporal sequence of two-dimensional image components of the video stream. It is conceivable to detect camera movement or zoom speed, which is then output as a recording property.

[0036] In embodiments of the method, in particular an orientation, a zoom factor of the respective video camera device providing the video stream data is automatically changed depending on the dynamically or statically recorded recording properties.

[0037] In embodiments of the method, the video stream does not contain any information data about the recording properties. Therefore, the recording property is preferably determined exclusively by comparing the associated two-dimensional image components with the data of the 3D model. In embodiments, the three-dimensional model data about the industrial plant can include a position of the video camera device(s). In embodiments, a zoom factor of the video camera device is determined depending on several temporally consecutive two-dimensional image data from the video camera device.

[0038] By comparing several chronologically successive image data and the object properties present in the three-dimensional model, a zoom factor or zoom speed can be determined.

[0039] In embodiments, the method comprises at least one of the following steps:

[0040] Transmitting the video stream to a processing platform;

[0041] Transferring the 3D model to the processing platform; and

[0042] Transmitting the determined recording property from the processing platform to a display device.

[0043] Preferably, the processing platform is configured as a cloud service. The processing platform can then be configured to perform the steps of assigning two-dimensional image components and determining the respective recording property in a computer-implemented manner in a secure processing environment.

[0044] The processing platform can be implemented, for example, using a Microsoft Azure environment or web services from other providers, such as AWS. The respective data is preferably transferred via secure and cryptographically protected communication protocols.

[0045] In embodiments, the processing platform is configured as an app that runs on a terminal device, such as a smartphone or tablet computer. The processing platform is then configured to perform the steps of assigning two-dimensional image components and determining the respective recording property in a computer-implemented manner in a secure processing environment of the terminal device.

[0046] In embodiments, the method comprises: receiving multiple video streams from different video camera devices.

[0047] The steps of assigning two-dimensional image components, determining a respective recording property, and outputting the video stream are preferably performed for each video stream and the associated video camera device using the respective 3D model for the respective industrial plant or plant component. In some embodiments, the same 3D model can be used; in other embodiments, different 3D models are used.

[0048] The video camera devices specifically capture different areas of the industrial facility, so that the capture direction of the respective two-dimensional image component of the respective video stream is determined depending on the orientation, positioning, and zoom setting of each video camera. Each video stream can thus be given additional context in the form of recording properties or object properties. A superimposed display of the video stream images and the additional properties is conceivable. Additional properties are understood to include, in particular, the camera data and the object data.

[0049] In embodiments, one of several video streams is selectively forwarded to a processing platform which is designed in the manner of a cloud service.

[0050] Furthermore, a device for carrying out the method for monitoring an industrial plant described above and below is proposed. A device comprises, in particular: a video camera device for generating the video stream of the industrial plant; a storage device for providing the three-dimensional model of the plant, in which respective object properties are assigned to the plant objects; a processing device for assigning two-dimensional image components of the video stream to plant objects using the 3D model and for determining the recording property; and / or a display device for outputting the video stream together with the determined object properties and / or recording properties, in particular as an overlay and an assignment to the 3D model.

[0051] The video camera device, the storage device, the processing device, and the display device are preferably communicatively linked. The functions of the processing device can be provided by software services in a cloud environment.

[0052] A respective method step or a functionalized device, for example, a processor unit or processing device, can be implemented in hardware and / or software. In a hardware implementation, the respective function can be embodied as a device or as part of a device, for example, as a computer or a microprocessor. In a software implementation, the respective unit can be embodied as a computer program product, as an app, a function, a routine, as part of a program code, or as an executable object, in particular as a software service in a cloud environment.

[0053] Furthermore, a computer program product is proposed which comprises computer-readable instructions which, when executed by a computer, cause the computer to carry out the method described above. A computer program product comprises, in particular, machine-readable instructions which, when executed by one or more processor devices of a processing environment, cause the execution of one or all method steps of the proposed method.

[0054] A computer program product, such as a computer program means, can be provided or delivered, for example, as a storage medium, such as a memory card, USB stick, CD-ROM, DVD, or in the form of a downloadable file from a server in a network. This can be done, for example, in a wireless communications network by transmitting a corresponding file with the computer program product or the computer program means.

[0055] The embodiments and features described for the proposed device apply accordingly to the proposed method.

[0056] Further possible implementations of the invention also include combinations of features or embodiments described above or below with respect to the exemplary embodiments not explicitly mentioned. In this case, the person skilled in the art will also add individual aspects as improvements or additions to the respective basic form of the invention.

[0057] Further advantageous embodiments and aspects of the invention are the subject of the dependent claims and the exemplary embodiments of the invention described below. The invention will be explained in more detail below using preferred embodiments with reference to the accompanying figures.

[0058] Fig. 1 shows a flowchart with process steps for a variant of a method for monitoring an industrial plant; Fig. 2 shows an expanded flowchart with process steps for a further variant of a method for monitoring an industrial plant;

[0059] Fig. 3 shows schematically an embodiment of a device for monitoring an industrial plant;

[0060] Fig. 4 shows a schematic representation of a video stream and an assignment of image components to plant objects to explain the method for monitoring an industrial plant; and

[0061] Fig. 5 shows an embodiment of a display device.

[0062] In the figures, identical or functionally equivalent elements have been given the same reference numerals unless otherwise stated.

[0063] Figs. 1 and 2 show flowcharts with method steps for an exemplary embodiment of a method for monitoring an industrial plant. The method steps are carried out in particular in an embodiment of a device for monitoring an industrial plant, as shown schematically in Fig. 3.

[0064] Fig. 3 shows a surveillance system or a device 1 in which an industrial plant 2, which can be, for example, a complex piping system, a factory, refinery, production line or even a logistics facility. A plant 2 that covers a geographically extensive spatial area can be recorded via one or more surveillance cameras 3, 4 that are designed as digital video cameras. In this case, video stream data is generated, in particular in real time. The video cameras 3, 4 used can be arranged at different positions in the area of ​​the plant 2 and, for example, can be pivoted or fixed. It is also conceivable for different cameras to be equipped with an optical zoom. This results in video streams that show different image sections that reproduce parts or objects of the plant 2.

[0065] The video stream data is shown in Fig. 3 as arrows pointing to the right and is transmitted to a local computing device 5, for example a control room. The video data supplied by the installed camera systems do not contain any information about the respective orientation, the zoom factor or, for example, focus settings of the cameras 3, 4. In Fig. 4, for example, a single image of a video stream VS is schematically indicated on the left. The industrial plant 2 is shown in simplified form with four plant objects A, B, C, D. The video stream VS also contains a representation of the surroundings of the industrial plant. It is now possible for one of the video cameras 3, 4 to focus on an image component PT, for example a pipe system C between two plant components B and D. In order to provide the personnel with more detailed and meaningful displays, a first method step (see Fig.1) receiving the video stream data VS (step S1).

[0066] Subsequently, in method steps S2 and S3, a relationship is created between an existing three-dimensional (3D) model of the monitored industrial plant 2, or its plant objects or components, and the image components of the video stream VS. For this purpose, in step S2, a respective two-dimensional image component PT, as indicated in Fig. 4, is assigned to a plant object of the industrial plant using a three-dimensional model, for example, a CAD (Computer-Aided Design) model of the industrial plant 2.

[0067] In the illustration in Fig. 4, the assignment can be seen by the dashed arrow. On the right-hand side of Fig. 4, a 3D model of the plant CAD is schematically illustrated. The plant objects A', B', C, D' present in the three-dimensional CAD model of the plant are provided with object properties. Detailed CAD data, for example, are available as object properties. The object properties can include the size, position, orientation in space, and other properties. In the example shown in Fig. 4, the image component PT, for example, represents pipes C that run horizontally and have certain flow materials. In this respect, object data can be retrieved from another database relating to the function of the industrial plant, which, for example, specifies a permissible surface temperature of pipes C.

[0068] In step S3, a camera property of the video camera 3, 4 that delivered the image component PT in the video stream VS is determined as a recording property of the image. For this purpose, the two-dimensional image data PT, which represents the system object C, namely the piping, is compared with the object properties present in the three-dimensional system model CAD. From this, for example, the position and / or orientation or viewing direction of the camera delivering the image section PT can be determined. Furthermore, a zoom factor of the respective camera can be derived from the knowledge of the position and image section PT. In this respect, a recording property, in particular the type of orientation, position, and zoom factor of the video camera device, can be recorded from the two-dimensional video stream data VS.In step S4, this context data, which includes the asset object data and the recording properties, is output together with the video stream.

[0069] In this respect, the proposed method provides image data-based tracking of the surveillance cameras 3, 4 deployed. In particular, the camera movement and zoom setting of each camera can be determined in real time. The computer-implemented evaluation and image processing of the video stream data can be performed using known methods, such as those used in connection with the Cyclicon software mentioned above. However, other algorithms are also conceivable that recognize a facility object present in a three-dimensional model based on two-dimensional image data. Algorithms are also known that recognize overlay points for the 3D model in a 2D image. Such algorithms can also be used here.

[0070] Referring to Fig. 3, which shows a cloud-based monitoring system for an industrial plant 2, the additional method steps or processes indicated in Fig. 2 are carried out. In a preparatory step S10, one or more video streams are generated using the video surveillance cameras 3, 4. The video stream data VS, schematically indicated on the left in Fig. 4, are fed to a control room computer 6 via a local computing system. The local computing system 5 receives, for example, the video stream data VS from the various surveillance cameras 3, 4 and prepares them for display on a screen. The corresponding data processing steps are carried out locally, which is indicated in Fig. 4 by the curly bracket LKL.

[0071] Since the received video stream data VS is available without any further context, in particular without knowledge of the location of the surveillance camera 3, 4 used, a display of the specific video stream data VS with additional information can be carried out for a user USR via a suitable terminal device, for example, a tablet computer or a mobile display device 8. For this purpose, a cloud platform 7, for example, using Microsoft Azure, is set up with a corresponding software service 10, 11. The cloud computing environment CLD is indicated by a dashed line in Fig. 4.

[0072] In particular, a 3D plant model service 10 and an app service 11 for communicative coupling with the user terminal 8 are provided as software services.

[0073] Fig. 3 further shows a database device 9, which is coupled to the cloud environment CLD via an interface 12. The database 9 contains corresponding 3D model data for the monitored industrial plant 2. This can be CAD data. Furthermore, the database 9 can contain additional information or context data about the plant objects installed in the plant 2. This can, for example, be the aforementioned information about flow materials of certain pipelines. The corresponding 3D plant model, or the 3D model data, is previously generated or provided in step S11. For example, such model data is generated during the design or planning of an industrial plant.

[0074] In step S12, the software service 10 instantiates the corresponding three-dimensional system model based on the 3D model data, for example, CAD data, received from the database 9. The software service of the cloud environment 7, designated 11, then essentially performs the method steps S1, S2, S3, and S4, which are summarized in Figs. 1 and 2 as processing step S100. The dashed double arrow indicates the communicative coupling of the terminal device 8, namely a display device 8 of the user USR, and the software service or app 11.

[0075] Fig. 5 shows a possible embodiment of display states of the terminal device 8. The terminal device is a display device 8 with a display 14 on which, for example, video stream data VS is displayed. Furthermore, the user terminal device 8, implemented as a display device, is provided with control elements 13. Using the control elements 13, the user USR can retrieve context information for the image data VS displayed on the display 14, for example, via a touchscreen function or other haptic elements.

[0076] For example, Fig. 5A shows the individual image shown on the left of the video stream VS in Fig. 4. Meanwhile, in the cloud environment CLD, the respective asset object data for the asset objects A, B, C, and D identified in the video stream VS is retrieved from the software service 10 via the software service 11. Furthermore, this object data is assigned as described for method step S2.

[0077] For example, the software service 11 can detect that the pipes C in the image component shown in dashed lines have an elevated temperature that does not correspond to the target temperature. If the user selects the displayed system area C, a zoomed-in display of the area with added or superimposed additional information XYZ, designated 15, is displayed, for example, as shown in Fig. 5B. The additional information 15 can, for example, represent a warning and indicate to the user a security event in the monitored system. Based on the camera information determined in method step S3, the user is able to switch back and forth between different cameras.By determining the recording properties with regard to orientation and zoom setting, the navigation and selection of the video stream images to be displayed using the display device 8 is simplified.

[0078] Overall, the proposed surveillance method allows for the enrichment of pure video stream data with contextual data, such as object properties stored in a 3D model, as well as the tracking of any camera pan or zoom. The proposed functionalities and the enhanced display of the video image data can be provided via a cloud environment and a cloud service using a suitable user interface on a display device.

[0079] Although the present invention has been described in detail using an exemplary embodiment, various modifications can be made. The image components exemplified, namely pipes, can be any system components. Furthermore, additional sensor data can be incorporated into the monitoring, such as images from spectral cameras. This can further improve monitoring performance. Instead of the aforementioned CAD data for the 3D models, other formats, such as OBJ or other formats, are also possible.

[0080] Reference symbol:

[0081] 1 plant monitoring system

[0082] 2 Appendix

[0083] 3 Video camera / surveillance camera

[0084] 4 Video camera / surveillance camera

[0085] 5 local computing device

[0086] 6 Control room

[0087] 7 Cloud environment

[0088] 8 Display device

[0089] 9 Database

[0090] 10 3D model

[0091] 11 App Service

[0092] 12 Interface

[0093] 13 controls

[0094] 14 Display

[0095] 15 Additional information

[0096] A, B, C, D Representation of a plant object in the video stream A', B', C, D' Plant object with object properties according to 3D model

[0097] PT image component

[0098] 51 Receiving a video stream

[0099] 52 Assigning 2D image component to asset object according to the 3D model

[0100] 53 Determining recording properties

[0101] 54 Outputting the video stream data with camera / object properties

[0102] 55 Adding context data to the video stream data

[0103] 510 Creating a video stream

[0104] 511 Creating a 3D plant model

[0105] 512 Instantiating a 3D plant model

[0106] VS Videostream

[0107] XYZ context, camera or additional information

Claims

Claims 1. Method for monitoring an industrial plant (2) with plant objects comprising the steps: Receiving (S1) a video stream (VS) from the system (2), which is generated using a video camera system (3), wherein the video stream (VS) contains a temporal sequence of two-dimensional image data; Assignment (S2) of two-dimensional image components (PT) of the video stream (VS) to plant objects (A 1 , B', C, D') using a three-dimensional (3D) model (CAD) of the plant (2), in which the plant objects (A 1 , B', C, D') are assigned respective object properties (XYZ); Determine (S3) a recording property of the image data depending on the image components (PT) assigned to one or more plant objects (C) and the respective object property (XYZ), wherein the recording property includes a position, an orientation and a zoom factor of the video camera device (3) which captures the video stream; and Output (S4) of the video stream (VS 1 ) together with the specific object properties (XYZ) and recording properties.

2. Method according to claim 1, wherein the industrial plant (2) is arranged on a plant site and the position of the video camera device (3) on the plant site is determined.

3. Method according to claim 2, wherein the video camera device (3) has a video recording area which is smaller than the site of the installation.

4. Method according to one of claims 1-3, wherein the video camera device (3) is mounted at an unknown position when receiving the video stream (VS).

5. Method according to any one of claims 1-4, wherein the object properties (XYZ) are a location, a size / dimension, a slant / orientation, a list of components, material properties and / or surface properties of the plant object (A 1 , B', C, D') include.

6. Method according to claims 1-5, further comprising: Creating (S11) a database (9) which contains the asset objects (A 1 , B', C, D') assigns further functional properties and / or context data, whereby the functional properties in particular process data, temperatures, flow materials, and the contextual data in particular time data, weather data and / or visibility conditions.

7. The method of claim 6, wherein the functional properties and / or context data are updated, in particular in real time.

8. Method according to one of claims 1-7, wherein the assignment (S2) is further dependent on functional properties of the plant objects (A 1 , B', C, D') is done.

9. Method according to any one of claims 1-8, wherein the three-dimensional model is a computer-aided design model of the industrial plant (2).

10. Method according to one of claims 1 - 9, wherein a dynamic recording property, in particular a camera movement or zoom speed, is determined by means of a temporal sequence of two-dimensional image components of the video stream (VS).

11. Method according to claim 10, wherein the camera movement and / or zoom speed is determined in real time.

12. Method according to one of claims 1 - 11, wherein the video stream (VS) does not contain any information data about the recording property, and the recording property is determined exclusively by comparing the associated two-dimensional image components (PT) and the data of the 3D model (CAD).

13. Method according to any one of claims 1 - 12, wherein the 3D model data includes a position of the video camera device (3).

14. Method according to one of claims 1 - 13, wherein a zoom factor is determined as a function of several temporally successive two-dimensional image data from the video camera device (3).

15. Method according to any one of claims 1-14, further comprising: Display (S5) the video stream (VS) together with the object properties (XYZ) and / or recording properties using a display device (8).

16. Method according to any one of claims 1-15, further comprising: Creating (S12) the three-dimensional (3D) model of the plant, assigning object properties (XYZ) to the plant objects.

17. Method according to any one of claims 1-16, further comprising: Transfer of the video stream (VS) to a processing platform (7); Transferring the 3D model (CAD) to the processing platform (7); and Transferring the specified recording property from the processing platform (7) to a display device (8); wherein the processing platform (7) is designed and configured as a cloud service (CLD) to perform the steps of assigning (S2) two-dimensional image components and determining (S3) the respective recording property in a secure processing environment (CLD) using computer implementation.

18. Method according to any one of claims 1-17, further comprising: Receiving multiple video streams (VS) from different video camera devices (3, 4); wherein the steps of assigning (S2) two-dimensional image components (PT), determining (S3) a respective recording property and outputting (S4) the video stream (VS) for each video stream and the associated video camera devices (3, 4) are performed using a respective 3D model (CAD).

19. Method according to claim 18, further comprising: selectively forwarding one of the multiple video streams to a processing platform (7), wherein the processing platform (7) is designed and configured in the manner of a cloud service (CLD) to perform the steps of assigning (S2) two-dimensional image components and determining (S3) the respective recording property in a secure processing environment using a computer implementation.

20. Computer program product comprising machine-readable instructions which, when executed by one or more processor units of a processing environment (CLD), cause the execution of one or all process steps of the method according to any one of claims 1-19.

21. Device (1) for carrying out the method according to one of claims 1 - 19, comprising: a video camera device (3, 4) for generating the video stream (VS) of the industrial plant (2); a storage device (9) for providing the three-dimensional (3D) model of the plant (2), in which the plant objects (A 1, B', C, D') respective object properties (XYZ) are assigned; a processing unit (10, 11) for assigning two-dimensional image components (PT) of the video stream (VS) to plant objects using the 3D model (10), and for determining the recording property; and with a display unit (8) for outputting the video stream (VS) together with the determined object properties and / or recording properties; wherein the video camera unit (3, 4), the storage unit (9), the processing unit (10, 11) and the display unit (8) are communicatively coupled to each other.

Images